PhoBERT Sentiment Analysis 🇻🇳

Fine-tuned PhoBERT model for Vietnamese product review sentiment classification (Positive / Neutral / Negative).

Usage

from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

model_name = "hiuS04/phobert-sentiment-api"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)

text = "Sản phẩm rất tốt và đáng tiền"
inputs = tokenizer(text, return_tensors="pt")
outputs = model(**inputs)
pred = torch.softmax(outputs.logits, dim=-1)
print(pred)
Downloads last month
18
Safetensors
Model size
0.1B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 3 Ask for provider support

Space using hiuS04/phobert-sentiment-api 1